CVE-2026-12491
A flaw was found in vLLM, an open-source library for large language …
A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB, transparency information may be implicitly discarded or remapped, leading to unexpected rendering of transparent pixels and distortion of input content. This can result in the model misinterpreting image content, potentially affecting the integrity of processed data.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- access.redhat.com/security/cve/CVE-2026-12491
- bugzilla.redhat.com/show_bug.cgi?id=2489786
- github.com/vllm-project/vllm/security/advisories/GHSA-8jr5-v98p-w75m
- github.com/vllm-project/vllm/pull/44974
- github.com/vllm-project/vllm/commit/cf1c90672404548aa3bc51f92c4745576a65ee26
- nvd.nist.gov/vuln/detail/CVE-2026-12491
- github.com/advisories/GHSA-8jr5-v98p-w75m
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3406.yaml
- nvd.nist.gov/vuln/detail/CVE-2026-12491
- cve.org/CVERecord?id=CVE-2026-12491
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.